Jagath Senarathne

DSC06688

Qualifications:

BSc Honours Degree in Statistics, University of Peradeniya, Sri Lanka

Research Interests

  • Bayesian experimental design
  • Bayesian modelling
  • Design of Experiments
  • Spatial Statistics

Project Description

Multiple response models are in existence where one response is nested within another (or responses share a dependence structure). There are many situations where multiple responses are measured during an experiment, such as drug efficacy and toxicity in pharmacology, disease and yield resistance of grains in agriculture, and so on. However, design of experiment for multivariate responses has not received much attention same as design for univariate responses. Recently, Copula functions have become a popular method to describe the dependencies between random variables (or responses). Thus, the lack of suitable methodologies to derive optimal designs for Copula models is a major issue of applying Copula models in the real world problems. Therefore, my research focuses on developing efficient computational algorithms to derive optimal Bayesian designs for Copula models. The proposed update of this research project will also concentrate on parallel computational designs to enable efficient computing, making efficient statistical methods feasible for practitioners and statisticians.

Publications:

  • Senarathne, S., & Wijekoon, P. (2016). A New Selection Index to Address within Course Competition and between Course Competition for Ranking Examination Scores. British Journal of Mathematics & Computer Science, 13(6), 1–17.  http://doi.org/10.9734/BJMCS/2016/23213
  • Senarathne, S., & Wijekoon, P. (2014). Skewness Based Common Currency Index Method for University Selection in Sri Lanka, Peradeniya University International Research Session (iPURSE), 18. http://www.pdn.ac.lk/ipurse/2014/proceeding_book/IS/392.pdf

Contact Details: